vllm-omni

attention

[Feat] Add native Mooncake KV transfer from AR to DiT (#7166 )

2026-09-20 14:44:55 +00:00

cache

[New Model] Ming-Image (inclusionAI/Ming-Image-0.1-Design) Support (#8021 )

2026-09-23 12:20:06 +00:00

diffusion_kv

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

distributed

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264 )

2026-09-23 18:26:53 +08:00

executor

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

hooks

[Perf][Diffusion] Skip the Ulysses length all-gather when shards are padded equal (#5717 )

2026-09-06 16:23:30 +08:00

interaction

[Core][Diffusion] Camera interaction for diffusion streaming generation (LingBot World 2 as example) (#7198 )

2026-09-20 16:19:41 +00:00

layers

[Bugfix][MiniMax-H3] Fix Hopper keyframe and modulation precision (#7913 )

2026-09-21 16:26:09 +08:00

lora

[Perf][Diffusion] Activate NPU/GPU matmul for LoRA delta computation when weights are on CPU (#7590 )

2026-09-18 16:51:23 +08:00

model_loader

[Bugfix] Isolate weekly CPU tests from inherited attention env and hf_api mocks (#7565 )

2026-09-21 15:55:00 +00:00

models

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

offloader

[Refactor][Diffusion] Resolve distributed layerwise topology in the plan (#7326 )

2026-09-19 19:05:18 +08:00

postprocess

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

profiler

[Bugfix] Report stepwise Qwen-Image profiler metrics (#4517 )

2026-07-03 04:32:22 +00:00

quantization

[Bugfix] Fix HSDP compatibility with the new online FP8 linear method (#5677 )

2026-08-14 15:45:55 +08:00

sched

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

utils

[5/N] Schedule chunk transfers as their own stage (#7406 )

2026-09-18 09:27:56 +08:00

worker

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

__init__.py

[Diffusion] Qwen image support (#82 )

2025-11-28 14:22:11 +08:00

compile.py

fix: keep DLO hooks outside regional compilation (#6073 )

2026-08-22 21:44:03 +08:00

config.py

[Diffusion][Attention] Support per-role attention backend via CLI (#2681 )

2026-05-10 11:59:05 +08:00

data.py

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

diffusion_engine.py

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

envs.py

[Kernel][Boogu-Image] Fuse Q/K RMSNorm + interleaved RoPE via fused_qk_norm_rope (#6982 )

2026-09-13 09:39:27 +08:00

forward_context.py

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

inline_stage_diffusion_client.py

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264 )

2026-09-23 18:26:53 +08:00

io_support.py

[Feature] Support text encoder Disaggregation for H3 (#5885 )

2026-08-28 14:27:05 +08:00

ipc.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

media.py

[Core][Diffusion] Add a typed pre-D2H video media contract (#6615 )

2026-09-10 09:50:54 +00:00

model_metadata.py

[Model][Frontend] MiniMax-H3: Add latent-mask editing (#7465 )

2026-09-20 03:54:44 +00:00

output_formatter.py

[Bugfix] Keep async video jobs queued until inference and abort on delete (#6759 )

2026-09-15 20:43:30 -07:00

registry.py

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00

request.py

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264 )

2026-09-23 18:26:53 +08:00

stage_diffusion_client.py

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264 )

2026-09-23 18:26:53 +08:00

stage_diffusion_proc.py

[Feature] Transfer AR-to-diffusion payloads over NIXL (#6264 )

2026-09-23 18:26:53 +08:00

vllm_config.py

[Diffusion][HunyuanImage3] Add request paged prefix caching (#7719 )

2026-09-23 15:34:56 +00:00